基于MATLAB的BP神经网络组合预测模型在公路货运量预测中的应用

详细信息 本馆镜像全文    |  推荐本文 | | 获取馆网全文

英文篇名：BP Neural Network Combination Forecasting Model Based on MATLAB Used in Highway Freight Volume Prediction 中文刊名：交通标准化 英文刊名：Transport Standardization 作者：杨云超 ; 吴非 ; 袁振洲 英文作者：YANG Yun-chao ; WU Fei ; YUAN Zhen-zhou (MOE Key Laboratory for Urban Transportation Complex Systems Theory and Technology ; Beijing Jiaotong University ; Beijing 100044 ; China) 中文关键词：BP神经网络 ; 货运量 ; MATLAB ; 组合预测 英文关键词：BP neural network ; freight volume ; MATLAB ; combination forecast 出版日期：2010-04-08 机构：北京交通大学城市交通复杂系统理论与技术教育部重点实验室; 年：2010 期：07 出版单位：交通标准化

摘要

采用BP神经网络建立公路货运量组合预测的理论模型,灵活利用神经网络通过自适应自学习能够拟合任意非线性函数的功能,有效克服传统的组合预测方法在实际应用中把数据间的关系强加给某一类函数的不足,并借助于先进的数学计算软件MATLAB进行简单的编程,大大降低模型的计算难度,实例证明该方法具有更高的预测精度。
A new theory model is brought forward and the model based on BP neural network is used in highway freight volume combination forecasting.This model flexibly applied the capability that the neural network can fit any non-linear function by self-adaptation and self-learning,avoiding the shortage effectively that traditional combination forecasting method forces the relationship among the data on some sort of function in the application.With the help of MATLAB,some simple program is compiled.It decreases the difficulty of calculation.The example has proved that this method has higher prediction precision.

引文

[1]杨浩.模型与算法[M].北京:北方交通大学出版社,2002,182-194.
    [2]董长虹.MATLAB神经网络与应用[M].北京:国防工业出版社,2007,64-104.
    [3]周传世.非线性权组合预测模型及其最优权的确定[J].预测,1994,(2):60-64.
    [4]沈花玉.BP神经网络隐含层单元个数的确定[J].天津理工大学学报,2008,(5):13-15.
    [5]温岩,乔兵.基于MATLAB工具箱的神经网络在地震预报中的应用[J].东北地震研究,2001,(3):36-40.
    [6]Hornik K,Strinchcomber M,Whiter H.Muti-layer Feedforward Networks are Universal Approxima-tors[J].Neural Networks,1989,(2):359-366.
    [7]Honik K.Approximation Capabilities of Multilayer Feedforward Networks Neural[J].Neural Network,1991,(4):551-557.